Simple and Effective Multi-Paragraph Reading Comprehension

@inproceedings{Clark2017SimpleAE,
  title={Simple and Effective Multi-Paragraph Reading Comprehension},
  author={Christopher Clark and Matt Gardner},
  booktitle={ACL},
  year={2017}
}
We consider the problem of adapting neural paragraph-level question answering models to the case where entire documents are given as input. Our proposed solution trains models to produce well calibrated confidence scores for their results on individual paragraphs. We sample multiple paragraphs from the documents during training, and use a shared-normalization training objective that encourages the model to produce globally correct output. We combine this method with a state-of-the-art pipeline… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 95 CITATIONS, ESTIMATED 99% COVERAGE

Document Gated Reader for Open-Domain Question Answering

  • SIGIR
  • 2019
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Natural Questions: A Benchmark for Question Answering Research

Tom Kwiatkowski, Jennimaria Palomaki, +15 authors Slav Petrov
  • Transactions of the Association for Computational Linguistics
  • 2019
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Effective Subword Segmentation for Text Comprehension

Zhuosheng Zhang, Zhao Hai, +4 authors Guohong Fu
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2018
VIEW 15 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Learning to Search in Long Documents Using Document Structure

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Read + Verify: Machine Reading Comprehension with Unanswerable Questions

  • AAAI
  • 2018
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 13 Highly Influenced Citations

  • Averaged 31 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES